© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78952
    Prev
    Next
    INDEX
    Explanations

    terragrunt.hcl, cagr, fuzzy matching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    il
    1.74
    ig
    1.74
    u
    1.72
    a
    1.67
    us
    1.40
    ern
    1.35
    y
    1.34
    و
    1.33
     It
    1.32
    ik
    1.29
    POSITIVE LOGITS
    ため
    1.43
    لي
    1.40
    ために
    1.40
    、
    1.34
    تك
    1.32
    ש
    1.32
     industriel
    1.29
    ليك
    1.27
     ﺍﻟ
    1.25
     mágico
    1.25
    Activations Density 0.000%

    No Known Activations